publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

2026

  1. Worldrft: Latent world model planning with reinforcement fine-tuning for autonomous driving
    2026
    Proceedings of the AAAI Conference on Artificial Intelligence 40 (14), 11649 …
  2. Unifying language-action understanding and generation for autonomous driving
    2026
    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …
  3. StreetForward: Perceiving Dynamic Street with Feedforward Causal Attention
    2026
    arXiv preprint arXiv:2603.19552
  4. Streamingclaw technical report
    2026
    arXiv preprint arXiv:2603.22120
  5. SparseWorld-TC: Trajectory-Conditioned Sparse Occupancy World Model
    2026
    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …
  6. Rlgf: Reinforcement learning with geometric feedback for autonomous driving video generation
    2026
    Advances in Neural Information Processing Systems 38, 128659-128684
  7. ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving
    2026
    arXiv preprint arXiv:2605.04647
  8. Planagent: A multi-modal large language agent for closed-loop vehicle motion planning
    2026
    IEEE Transactions on Cognitive and Developmental Systems
  9. Metis: A Generalizable and Efficient World-Action Model for Autonomous Driving and Urban Navigation
    2026
    arXiv preprint arXiv:2606.15869
  10. Method and apparatus for generating trajectory, electronic device, storage medium
    2026
    US Patent App. 19/037,583
  11. M2A: Synergizing Mathematical and Agentic Reasoning in Large Language Models
    2026
    arXiv preprint arXiv:2605.09879
  12. LiAuto-GeoX: Efficient Grounded Driving Transformer
    2026
    arXiv preprint arXiv:2606.05774
  13. Hardware Co-Design Scaling Laws via Roofline Modelling for On-Device LLMs
    2026
    arXiv preprint arXiv:2602.10377
  14. FAAR: Format-Aware Adaptive Rounding for NVFP4
    2026
    arXiv preprint arXiv:2603.22370
  15. Evolving from Tool User to Creator via Training-Free Experience Reuse in Multimodal Reasoning
    2026
    arXiv preprint arXiv:2602.01983
  16. Evaluating the Search Agent in a Parallel World
    2026
    arXiv preprint arXiv:2603.04751
  17. DriveLiDAR4D: Sequential and Controllable LiDAR Scene Generation for Autonomous Driving
    2026
    Proceedings of the AAAI Conference on Artificial Intelligence 40 (4), 2525-2533
  18. DriveCombo: Benchmarking Compositional Traffic Rule Reasoning in Autonomous Driving
    2026
    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …
  19. Correctad: A self-correcting agentic system to improve end-to-end planning in autonomous driving
    2026
    Proceedings of the AAAI Conference on Artificial Intelligence 40 (10), 7755-7763
  20. Closed Loop Dynamic Driving Data Mixture for Real-Synthetic Co-Training
    2026
    arXiv preprint arXiv:2605.21372
  21. Ad-r1: Closed-loop reinforcement learning for end-to-end autonomous driving with impartial world models
    2026
    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …

2025

  1. Transdiffuser: End-to-end trajectory generation with decorrelated multi-modal representation for autonomous driving
    2025
    arXiv e-prints, arXiv: 2505.09315
  2. Transdiffuser: Diverse trajectory generation with decorrelated multi-modal representation for end-to-end autonomous driving
    2025
    arXiv preprint arXiv:2505.09315
  3. The better you learn, the smarter you prune: Towards efficient vision-language-action models via differentiable token pruning
    2025
    arXiv preprint arXiv:2509.12594
  4. StyledStreets: Multi-style Street Simulator with Spatial and Temporal Consistency
    2025
    arXiv preprint arXiv:2503.21104
  5. Streetcrafter: Street view synthesis with controllable video diffusion models
    2025
    Proceedings of the Computer Vision and Pattern Recognition Conference, 822-832
  6. Street Gaussians: Modeling Dynamic Urban Scenes With Gaussian Primitives
    2025
    IEEE transactions on pattern analysis and machine intelligence
  7. RoboPearls: editable video simulation for robot manipulation
    2025
    Proceedings of the IEEE/CVF International Conference on Computer Vision …
  8. Recondreamer: Crafting world models for driving scene reconstruction via online restoration
    2025
    Proceedings of the Computer Vision and Pattern Recognition Conference, 1559-1569
  9. PosePilot: Steering camera pose for generative world models with self-supervised depth
    2025
    IEEE/RSJ International Conference on Intelligent Robots and Systems …
  10. Omnigen: Unified multimodal sensor generation for autonomous driving
    2025
    Proceedings of the 33rd ACM International Conference on Multimedia, 9365-9374
  11. Learning Personalized Driving Styles via Reinforcement Learning from Human Feedback
    2025
    arXiv preprint arXiv:2503.10434
  12. HiNeuS: High-fidelity Neural Surface Mitigating Low-texture and Reflective Ambiguity
    2025
    Proceedings of the IEEE/CVF International Conference on Computer Vision …
  13. Hierarchy UGP: Hierarchy Unified Gaussian Primitive for Large-Scale Dynamic Scene Reconstruction
    2025
    Proceedings of the IEEE/CVF International Conference on Computer Vision …
  14. Geodrive: 3d geometry-informed driving world model with precise action control
    2025
    arXiv preprint arXiv:2505.22421
  15. Generalizing motion planners with mixture of experts for autonomous driving
    2025
    IEEE International Conference on Robotics and Automation (ICRA), 6033-6039
  16.  Finetuning generative trajectory model with reinforcement learning from human feedback
    Finetuning generative trajectory model with reinforcement learning from human feedback
    2025
    arXiv e-prints, arXiv: 2503.10434
  17. Drivingsphere: Building a high-fidelity 4d world for closed-loop simulation
    2025
    Proceedings of the Computer Vision and Pattern Recognition Conference, 27531 …
  18. DriveAgent-R1: Advancing VLM-based autonomous driving with hybrid thinking and active perception
    2025
    arXiv e-prints, arXiv: 2507.20879
  19. DriveAgent-R1: Advancing VLM-based Autonomous Driving with Active Perception and Hybrid Thinking
    2025
    arXiv preprint arXiv:2507.20879
  20. Dive: Efficient multi-view driving scenes generation based on video diffusion transformer
    2025
    arXiv preprint arXiv:2504.19614
  21. Discrete diffusion for reflective vision-language-action models in autonomous driving
    2025
    arXiv preprint arXiv:2509.20109
  22. Bev-tsr: Text-scene retrieval in bev space for autonomous driving
    2025
    Proceedings of the AAAI Conference on Artificial Intelligence 39 (7), 7275-7283
  23. 3drealcar: An in-the-wild rgb-d car dataset with 360-degree views
    2025
    Proceedings of the IEEE/CVF International Conference on Computer Vision …

2024

  1. Xiaoxiao Long, Yilun Chen, and Hao Zhao. Tod3cap: Towards 3d dense captioning in outdoor scenes
    2024
    Computer Vision–ECCV, 367-384
  2. Unleashing generalization of end-to-end autonomous driving with controllable long video generation
    2024
    arXiv preprint arXiv:2406.01349
  3. Ua-track: Uncertainty-aware end-to-end 3d multi-object tracking
    2024
    arXiv e-prints, arXiv: 2406.02147
  4. Tod3cap: Towards 3d dense captioning in outdoor scenes
    2024
    European Conference on Computer Vision, 367-384
  5.  Street gaussians: Modeling dynamic urban scenes with gaussian splatting
    Street gaussians: Modeling dynamic urban scenes with gaussian splatting
    2024
    European Conference on Computer Vision, 156-173
  6. S2-track: A simple yet strong approach for end-to-end 3d multi-object tracking
    2024
    arXiv preprint arXiv:2406.02147
  7.  Drivevlm: The convergence of autonomous driving and large vision-language models
    Drivevlm: The convergence of autonomous driving and large vision-language models
    2024
    arXiv preprint arXiv:2402.12289
  8. Dive: Dit-based video generation with enhanced control
    2024
    arXiv preprint arXiv:2409.01595
  9. Bev-clip: Multi-modal bev retrieval methodology for complex scene in autonomous driving
    2024
  10. Balanced 3DGS: Gaussian-wise parallelism rendering with fine-grained tiling
    2024
    arXiv preprint arXiv:2412.17378

2023

  1. Street gaussians for modeling dynamic urban scenes.(2023)
    2023
    arXiv preprint arXiv:2401.01339

2015

  1. Joint tracking and classification with constraints and reassignment by radar and ESM
    L Xu H Jiang
    2015
    Digital Signal Processing 40, 213-223

2014

  1. Particle filter based joint tracking and classification
    2014
    Proceedings of IEEE Chinese Guidance, Navigation and Control Conference …
  2. Joint tracking and classification on aerodynamic model and RCS by ground-based passive radar
    2014
    Proceedings of IEEE Chinese Guidance, Navigation and Control Conference …
  3. Joint tracking and classification based on aerodynamic model and radar cross section
    K Zhan H Jiang
    2014
    Pattern recognition 47 (9), 3096-3105